{"id":"https://openalex.org/W2115630042","doi":"https://doi.org/10.1109/taslp.2014.2364130","title":"Feature Mapping of Multiple Beamformed Sources for Robust Overlapping Speech Recognition Using a Microphone Array","display_name":"Feature Mapping of Multiple Beamformed Sources for Robust Overlapping Speech Recognition Using a Microphone Array","publication_year":2014,"publication_date":"2014-10-20","ids":{"openalex":"https://openalex.org/W2115630042","doi":"https://doi.org/10.1109/taslp.2014.2364130","mag":"2115630042"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2014.2364130","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2364130","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/202572","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100444148","display_name":"Weifeng Li","orcid":"https://orcid.org/0000-0002-1410-8966"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weifeng Li","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, China","Shenzhen Key Laboratory of Information Science and Technology, Shenzhen Engineering Laboratory of IS&DRM, Department of Electronic Engineering, Graduate School at Shenzhen, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen Key Laboratory of Information Science and Technology, Shenzhen Engineering Laboratory of IS&DRM, Department of Electronic Engineering, Graduate School at Shenzhen, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101745213","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-8094-6861"},"institutions":[{"id":"https://openalex.org/I119806805","display_name":"Nagaoka University","ror":"https://ror.org/02rcadd38","country_code":"JP","type":"education","lineage":["https://openalex.org/I119806805"]},{"id":"https://openalex.org/I85922643","display_name":"Nagaoka University of Technology","ror":"https://ror.org/00ys1hz88","country_code":"JP","type":"education","lineage":["https://openalex.org/I85922643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["Nagaoka University of Technology, Japan","Longbiao Wang is with Nagaoka University of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Nagaoka University of Technology, Japan","institution_ids":["https://openalex.org/I119806805","https://openalex.org/I85922643"]},{"raw_affiliation_string":"Longbiao Wang is with Nagaoka University of Technology, Japan","institution_ids":["https://openalex.org/I85922643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009595085","display_name":"Yicong Zhou","orcid":"https://orcid.org/0000-0002-4487-6384"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Yicong Zhou","raw_affiliation_strings":["Department of Computer and Information Science, University of Macau, Macau, China","[Department of Computer and information science, University of Macau, Macau, China]"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498"]},{"raw_affiliation_string":"[Department of Computer and information science, University of Macau, Macau, China]","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105301736","display_name":"John Dines","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"John Dines","raw_affiliation_strings":["Idiap Research Inistitute, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Inistitute, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043551083","display_name":"Mathew Magimai.-Doss","orcid":"https://orcid.org/0000-0002-8714-1409"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mathew Magimai.-Doss","raw_affiliation_strings":["Idiap Research Inistitute, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Inistitute, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Herve Bourlard","raw_affiliation_strings":["Idiap Research Inistitute, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Inistitute, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009239895","display_name":"Qingmin Liao","orcid":"https://orcid.org/0000-0002-7509-3964"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingmin Liao","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, China","Shenzhen Key Laboratory of Information Science and Technology, Shenzhen Engineering Laboratory of IS&DRM, Department of Electronic Engineering, Graduate School at Shenzhen, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen Key Laboratory of Information Science and Technology, Shenzhen Engineering Laboratory of IS&DRM, Department of Electronic Engineering, Graduate School at Shenzhen, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100444148"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.1769,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.79993158,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"22","issue":"12","first_page":"2244","last_page":"2255"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7980912327766418},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.659220278263092},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6564139723777771},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6429738402366638},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6214311718940735},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5442032217979431},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5430154800415039},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5282917022705078},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4173971712589264}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7980912327766418},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.659220278263092},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6564139723777771},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6429738402366638},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6214311718940735},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5442032217979431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5430154800415039},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5282917022705078},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4173971712589264},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2014.2364130","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2364130","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:infoscience.epfl.ch:202572","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/202572","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:202572","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/202572","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W14578209","https://openalex.org/W1480376833","https://openalex.org/W1494747370","https://openalex.org/W1496189116","https://openalex.org/W1510095622","https://openalex.org/W1546892833","https://openalex.org/W1553407966","https://openalex.org/W1554663460","https://openalex.org/W1558276682","https://openalex.org/W1576049859","https://openalex.org/W1593898523","https://openalex.org/W1595191759","https://openalex.org/W1687555731","https://openalex.org/W1984541135","https://openalex.org/W2015631279","https://openalex.org/W2021092941","https://openalex.org/W2032595071","https://openalex.org/W2038054257","https://openalex.org/W2062164080","https://openalex.org/W2069976350","https://openalex.org/W2098441927","https://openalex.org/W2100969003","https://openalex.org/W2101609516","https://openalex.org/W2108661465","https://openalex.org/W2115483887","https://openalex.org/W2116623987","https://openalex.org/W2121573996","https://openalex.org/W2123649031","https://openalex.org/W2124776405","https://openalex.org/W2132122635","https://openalex.org/W2137075158","https://openalex.org/W2144244295","https://openalex.org/W2144679390","https://openalex.org/W2146172290","https://openalex.org/W2160815625","https://openalex.org/W2161176017","https://openalex.org/W2184045248","https://openalex.org/W2296581541","https://openalex.org/W2405774341","https://openalex.org/W4310638450","https://openalex.org/W4388297464","https://openalex.org/W6602857490","https://openalex.org/W6629669190","https://openalex.org/W6676449801","https://openalex.org/W6678429839","https://openalex.org/W6681430769","https://openalex.org/W6697251715","https://openalex.org/W6713658392"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2011788874","https://openalex.org/W2041060376","https://openalex.org/W2963983801","https://openalex.org/W3119734852"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,22,53,100],"nonlinear":[4,101],"vector-based":[5],"feature":[6,40,82],"mapping":[7,48,83,96,102],"approach":[8,127],"to":[9,34,90],"extract":[10],"robust":[11],"features":[12,105],"for":[13],"automatic":[14],"speech":[15,20],"recognition":[16,76],"(ASR)":[17],"of":[18,32,38,49,94,103,124],"overlapping":[19,141],"using":[21,67],"microphone":[23],"array.":[24],"We":[25,120],"explore":[26],"different":[27,50,85],"configurations":[28],"and":[29,60,116,140],"additional":[30],"sources":[31,51],"information":[33],"improve":[35,74,91],"the":[36,39,45,64,68,75,81,92,95,104,114,122,125,132],"effectiveness":[37,123],"mapping.":[41],"First,":[42],"we":[43,79,98],"investigate":[44,80],"full-vector":[46],"based":[47],"in":[52,88],"log":[54],"mel-filterbank":[55],"energy":[56],"(log":[57],"MFBE)":[58],"domain,":[59],"demonstrate":[61,121],"that":[62],"retraining":[63],"acoustic":[65],"model":[66],"generated":[69],"training":[70],"data":[71],"can":[72],"help":[73],"performance.":[77],"Then":[78],"between":[84],"domains.":[86],"Finally":[87],"order":[89],"qualities":[93],"inputs":[97],"propose":[99],"from":[106],"multiple":[107],"beamformed":[108],"sources,":[109],"which":[110,135],"are":[111],"directed":[112],"at":[113],"target":[115],"interfering":[117],"speakers,":[118],"respectively.":[119],"proposed":[126],"through":[128],"extensive":[129],"evaluations":[130],"on":[131],"MONC":[133],"corpus,":[134],"includes":[136],"non-overlapping":[137],"single":[138],"speaker":[139],"multi-speaker":[142],"conditions.":[143]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}